| Skeleton-contrastive 3D action representation learning FM Thoker, H Doughty, CGM Snoek Proceedings of the 29th ACM international conference on multimedia, 1655-1663, 2021 | 123 | 2021 |
| Cross-modal knowledge distillation for action recognition FM Thoker, J Gall 2019 IEEE International Conference on Image Processing (ICIP), 6-10, 2019 | 104 | 2019 |
| How severe is benchmark-sensitivity in video self-supervised learning? FM Thoker, H Doughty, P Bagad, CGM Snoek European Conference on Computer Vision, 632-652, 2022 | 22 | 2022 |
| Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization FM Thoker, H Doughty, CGM Snoek Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 9 | 2023 |
| Feature-supervised action modality transfer FM Thoker, CGM Snoek 2020 25th International Conference on Pattern Recognition (ICPR), 3751-3758, 2021 | 1 | 2021 |
| SIGMA: Sinkhorn-Guided Masked Video Modeling M Salehi, M Dorkenwald, FM Thoker, E Gavves, CGM Snoek, YM Asano European Conference on Computer Vision, 293-312, 2025 | | 2025 |
| LocoMotion: Learning Motion-Focused Video-Language Representations H Doughty, FM Thoker, CGM Snoek arXiv preprint arXiv:2410.12018, 2024 | | 2024 |
| Video-efficient foundation models FM Thoker | | 2023 |
| Supplementary Material SIGMA: Sinkhorn-Guided Masked Video Modeling M Salehi, M Dorkenwald, FM Thoker, E Gavves, CGM Snoek, YM Asano | | |
